| from transformers.configuration_utils import PretrainedConfig | |
| from transformers.modeling_rope_utils import rope_config_validation | |
| from .configuration_siglip2 import Siglip2VisionConfig | |
| YOUTU_PRETRAINED_CONFIG_ARCHIVE_MAP = {} | |
| class YoutuVLConfig(PretrainedConfig): | |
| r""" | |
| Args: | |
| vocab_size (`int`, *optional*, defaults to 129280): | |
| Vocabulary size of the Deep model. Defines the number of different tokens that can be represented by the | |
| `inputs_ids` passed when calling [`YoutuModel`] | |
| hidden_size (`int`, *optional*, defaults to 7168): | |
| Dimension of the hidden representations. | |
| intermediate_size (`int`, *optional*, defaults to 18432): | |
| Dimension of the MLP representations. | |
| num_hidden_layers (`int`, *optional*, defaults to 61): | |
| Number of hidden layers in the Transformer decoder. | |
| num_attention_heads (`int`, *optional*, defaults to 128): | |
| Number of attention heads for each attention layer in the Transformer decoder. | |
| num_key_value_heads (`int`, *optional*, defaults to 128): | |
| This is the number of key_value heads that should be used to implement Grouped Query Attention. If | |
| `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if | |
| `num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When | |
| converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed | |
| by meanpooling all the original heads within that group. For more details checkout [this | |
| paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to | |
| `num_attention_heads`. | |
| n_shared_experts (`int`, *optional*, defaults to 1): | |
| Number of shared experts. | |
| n_routed_experts (`int`, *optional*, defaults to 256): | |
| Number of routed experts. | |
| routed_scaling_factor (`float`, *optional*, defaults to 2.5): | |
| Scaling factor or routed experts. | |
| kv_lora_rank (`int`, *optional*, defaults to 512): | |
| Rank of the LoRA matrices for key and value projections. | |
| q_lora_rank (`int`, *optional*, defaults to 1536): | |
| Rank of the LoRA matrices for query projections. | |
| qk_rope_head_dim (`int`, *optional*, defaults to 64): | |
| Dimension of the query/key heads that use rotary position embeddings. | |
| v_head_dim (`int`, *optional*, defaults to 128): | |
| Dimension of the value heads. | |
| qk_nope_head_dim (`int`, *optional*, defaults to 128): | |
| Dimension of the query/key heads that don't use rotary position embeddings. | |
| n_group (`int`, *optional*, defaults to 8): | |
| Number of groups for routed experts. | |
| topk_group (`int`, *optional*, defaults to 4): | |
| Number of selected groups for each token. | |
| num_experts_per_tok (`int`, *optional*, defaults to 8): | |
| Number of selected experts, None means dense model. | |
| norm_topk_prob (`bool`, *optional*, defaults to `True`): | |
| Whether to normalize the weights of the routed experts. | |
| hidden_act (`str` or `function`, *optional*, defaults to `"silu"`): | |
| The non-linear activation function (function or string) in the decoder. | |
| max_position_embeddings (`int`, *optional*, defaults to 4096): | |
| The maximum sequence length that this model might ever be used with. | |
| initializer_range (`float`, *optional*, defaults to 0.02): | |
| The standard deviation of the truncated_normal_initializer for initializing all weight matrices. | |
| rms_norm_eps (`float`, *optional*, defaults to 1e-06): | |
| The epsilon used by the rms normalization layers. | |
| use_cache (`bool`, *optional*, defaults to `True`): | |
| Whether or not the model should return the last key/values attentions (not used by all models). Only | |
| relevant if `config.is_decoder=True`. | |
| pad_token_id (`int`, *optional*): | |
| Padding token id. | |
| bos_token_id (`int`, *optional*, defaults to 0): | |
| Beginning of stream token id. | |
| eos_token_id (`int`, *optional*, defaults to 1): | |
| End of stream token id. | |
| pretraining_tp (`int`, *optional*, defaults to 1): | |
| Experimental feature. Tensor parallelism rank used during pretraining. Please refer to [this | |
| document](https://huggingface.co/docs/transformers/parallelism) to understand more about it. This value is | |
| necessary to ensure exact reproducibility of the pretraining results. Please refer to [this | |
| issue](https://github.com/pytorch/pytorch/issues/76232). | |
| tie_word_embeddings (`bool`, *optional*, defaults to `False`): | |
| Whether to tie weight embeddings | |
| rope_theta (`float`, *optional*, defaults to 10000.0): | |
| The base period of the RoPE embeddings. | |
| rope_scaling (`Dict`, *optional*): | |
| Dictionary containing the scaling configuration for the RoPE embeddings. Currently supports two scaling | |
| strategies: linear and dynamic. Their scaling factor must be a float greater than 1. The expected format is | |
| `{"type": strategy name, "factor": scaling factor}`. When using this flag, don't update | |
| `max_position_embeddings` to the expected new maximum. | |
| rope_interleave (`bool`, *optional*, defaults to `True`): | |
| Whether to interleave the rotary position embeddings. | |
| attention_bias (`bool`, defaults to `False`, *optional*, defaults to `False`): | |
| Whether to use a bias in the query, key, value and output projection layers during self-attention. | |
| attention_dropout (`float`, *optional*, defaults to 0.0): | |
| The dropout ratio for the attention probabilities. | |
| """ | |
| sub_configs = {"vision_config": Siglip2VisionConfig} | |
| model_type = "youtu_vl" | |
| keys_to_ignore_at_inference = ["past_key_values"] | |
| base_model_pp_plan = { | |
| "embed_tokens": (["input_ids"], ["inputs_embeds"]), | |
| "layers": (["hidden_states", "attention_mask"], ["hidden_states"]), | |
| "norm": (["hidden_states"], ["hidden_states"]), | |
| } | |
| def __init__( | |
| self, | |
| vocab_size=129280, | |
| hidden_size=7168, | |
| intermediate_size=18432, | |
| num_hidden_layers=61, | |
| num_attention_heads=128, | |
| num_key_value_heads=128, | |
| n_shared_experts=1, | |
| n_routed_experts=256, | |
| routed_scaling_factor=2.5, | |
| kv_lora_rank=512, | |
| q_lora_rank=1536, | |
| qk_rope_head_dim=64, | |
| v_head_dim=128, | |
| qk_nope_head_dim=128, | |
| n_group=8, | |
| topk_group=4, | |
| num_experts_per_tok=8, | |
| norm_topk_prob=True, | |
| hidden_act="silu", | |
| max_position_embeddings=4096, | |
| initializer_range=None, | |
| embedding_initializer_range=None, | |
| rms_norm_eps=1e-6, | |
| use_cache=True, | |
| pad_token_id=None, | |
| bos_token_id=0, | |
| eos_token_id=1, | |
| pretraining_tp=1, | |
| tie_word_embeddings=False, | |
| rope_theta=10000.0, | |
| rope_scaling=None, | |
| rope_interleave=True, | |
| attention_bias=False, | |
| attention_dropout=0.0, | |
| vision_config=None, | |
| **kwargs, | |
| ): | |
| if isinstance(vision_config, dict): | |
| self.vision_config = self.sub_configs["vision_config"](**vision_config) | |
| elif vision_config is None: | |
| self.vision_config = self.sub_configs["vision_config"]() | |
| self.vocab_size = vocab_size | |
| self.max_position_embeddings = max_position_embeddings | |
| self.hidden_size = hidden_size | |
| self.intermediate_size = intermediate_size | |
| self.num_hidden_layers = num_hidden_layers | |
| self.num_attention_heads = num_attention_heads | |
| self.n_shared_experts = n_shared_experts | |
| self.n_routed_experts = n_routed_experts | |
| self.routed_scaling_factor = routed_scaling_factor | |
| self.kv_lora_rank = kv_lora_rank | |
| self.q_lora_rank = q_lora_rank | |
| self.qk_rope_head_dim = qk_rope_head_dim | |
| self.v_head_dim = v_head_dim | |
| self.qk_nope_head_dim = qk_nope_head_dim | |
| self.qk_head_dim = qk_nope_head_dim + qk_rope_head_dim | |
| self.head_dim = qk_rope_head_dim | |
| self.n_group = n_group | |
| self.topk_group = topk_group | |
| self.num_experts_per_tok = num_experts_per_tok | |
| self.norm_topk_prob = norm_topk_prob | |
| self.rope_interleave = rope_interleave | |
| self.flash_att_sliding_window = None | |
| self.mlp_bias = False | |
| self.mtp_loss_weight = 0.3 | |
| if num_key_value_heads is None: | |
| num_key_value_heads = num_attention_heads | |
| self.num_key_value_heads = num_key_value_heads | |
| self.hidden_act = hidden_act | |
| self.initializer_range = ( | |
| (2.0 / (5.0 * self.hidden_size)) ** 0.5 | |
| if initializer_range is None | |
| else initializer_range | |
| ) | |
| self.embedding_initializer_range = ( | |
| self.initializer_range * 2.0 | |
| if embedding_initializer_range is None | |
| else embedding_initializer_range | |
| ) | |
| self.rms_norm_eps = rms_norm_eps | |
| self.pretraining_tp = pretraining_tp | |
| self.use_cache = use_cache | |
| self.rope_theta = rope_theta | |
| self.rope_scaling = rope_scaling | |
| self.attention_bias = attention_bias | |
| self.attention_dropout = attention_dropout | |
| if self.rope_scaling is not None and "type" in self.rope_scaling: | |
| self.rope_scaling["rope_type"] = self.rope_scaling["type"] | |
| rope_config_validation(self) | |
| super().__init__( | |
| pad_token_id=pad_token_id, | |
| bos_token_id=bos_token_id, | |
| eos_token_id=eos_token_id, | |
| tie_word_embeddings=tie_word_embeddings, | |
| **kwargs, | |
| ) | |
| __all__ = ["YoutuVLConfig"] | |